This report observes the potential impact of mentorship on success factors for LEADS scholars. The outcome Y variables of success factors will be compared against the X variables ‘priaccess’ or ‘My primary mentor of mentoring team is accessible’, and ‘prioverall’ or ‘Please rate the overall effectiveness of your primary mentor.’ The data is unaggregated.

The LEADS survey has been broken down into subscales that will be assessed in the tabs belows.

Test of Statistical Power for Regression Analysis 
## 
## Call:
## lm(formula = burnout ~ priaccess, data = plot_data)
## 
## Residuals:
##     Min      1Q  Median      3Q     Max 
## -1.7638 -0.5299 -0.2959  0.7041  2.7041 
## 
## Coefficients:
##             Estimate Std. Error t value Pr(>|t|)    
## (Intercept)  3.46549    0.33582  10.319  < 2e-16 ***
## priaccess   -0.23391    0.07601  -3.077  0.00238 ** 
## ---
## Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
## 
## Residual standard error: 0.9955 on 198 degrees of freedom
## Multiple R-squared:  0.04565,    Adjusted R-squared:  0.04083 
## F-statistic:  9.47 on 1 and 198 DF,  p-value: 0.002384

 Multiple regression power calculation 

          u = 1
          v = 198
         f2 = 0.04782827
  sig.level = 0.05
      power = 0.8681824

Interpretation:

One predictor variable (priaccess). A small effect size, indicating that while there is a relationship with burnout, it explains only a small portion of the variance. A high power (87%), suggesting that your study is well-equipped to detect a significant relationship if it exists, given your sample size and effect size.

scatterplots

Burnout

Burnout, shown on the y-axis, is measured on a Likert Scale of 1 to 5, where 1 = None, 2 = Some Stress, 3 = Onset, 4 = Persistence, and 5 = Severe. In this case, low scores indicate a positive result.

The following plots show the same unaggregated data with a weighted regression line applied. Weighted regression was chosen to account for the reflection of n in the plot bubble sizes, aka how many scholars responded with each combination of scores.

Creativity

Passion and Interests

Passion and Interest variables on the y-axis are measured on a Likert Scale of 1 to 5, where 1 = Not at all, 2 = A little, 3 = Neutral, 4 = A lot, 5 = Very Much.

Leadership

Leadership variables on the y-axis are measured on a Likert Scale of 1 to 7, where 1 = Seldom and 7 = Almost Always.

Research Skills Inventory

Research Skills Inventory variables on the y-axis are measured on a Likert Scale of 0 to 10. Scholars were asked: Please indicate your ability to successfully perform each task by selecting a single number from 0 – 10 that best describes your level of confidence. We would like to know how confident you are that you can successfully perform these tasks TODAY where 0 = No confidence, 10 = Total confidence.

Professionalism

Professionalism variables on the y-axis are measured on a Likert Scale of 1 to 5, where 1 = Never and 5 = A great deal.

Research Experience

Research experience, seen on the y-axis, is measured on a Likert Scale of 0 to 5, where 0 = Has not changed at all, and 5 = Has changed a great deal.

Networking/Social Capital

Networking and social capital variables on the y-axis are measured on a Likert Scale of 0 to 10, where 0 = Not at all, 10 = Completely.

Job Satisfaction

Job satisfaction variables on the y-axis are measured on a Likert Scale of 1 to 7, where 1 = Strongly disagree and 7 = Strongly agree.

Career Satisfaction

Career satisfaction variables on the y-axis are measured on a Likert Scale of 1 to 5, where 1 = Not satisfied, 5 = Very satisfied.

Career Adapt-Abilities Inventory

Career Adat-Abilities Inventory variables on the y-axis are measured on a Likert Scale of 1 to 5. Scholars were provided with the following promt: Different people use different strength to build their careers. No one is good at everything, each of us emphasizes some strengths more than others. Please rate how strongly you have developed each of the following abilities using the scale below where 1 = Not strong and 5 = Strongest.